Search

Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying performance, a major limitation of prompt learning is the demand for labelled data. In real-world scenarios, we may only obtain candidate labels (where the true label is included) instead of the true labels due to data privacy or sensitivity issues. In this paper, we provide the first study on prompt learning with candidate labels for VLMs. We empirically demonstrate that prompt learning is more advantageous than other fine-tuning methods, for handling candidate labels. Nonetheless, its performance drops when the label ambiguity increases. In order to improve its robustness, we propose a simple yet effective framework that better leverages the prior knowledge of VLMs to guide the learning process with candidate labels. Specifically, our framework disambiguates candidate labels by aligning the model output with the mixed class posterior jointly predicted by both the learnable and the handcrafted prompt. Besides, our framework can be equipped with various off-the-shelf training objectives for learning with candidate labels to further improve their performance. Extensive experiments demonstrate the effectiveness of our proposed framework.

In recent years, the emergence of DNA storage systems has led to a widespread focus on the research of codes correcting insertions, deletions, and classic substitutions. During the initial investigation, Levenshtein discovered the VT codes are precisely capable of correcting single insertion/deletion and then extended the VT construction to single-insertion/deletion/substitution ($1$-ins/del/sub) correcting codes. Inspired by this, we generalize the recent findings of $1$-del $1$-sub correcting codes with redundancy $6\log_{2}n+O(1)$ to more general $2$-ins/del/sub correcting codes without increasing the redundancy. Our key technique is to apply higher-order VT syndromes to distinct objects and accomplish a systematic classification of all error patterns.

Node repair is a crucial problem in erasure-code-based distributed storage systems. An important metric for repair efficiency is the I/O cost which equals the total amount of data accessed at helper nodes to repair a failed node. In this work, a general formula for computing the I/O cost of linear repair schemes is derived from a new perspective, i.e., by investigating the Hamming weight of a related linear space. Applying the formula to Reed-Solomon (RS) codes, we obtain lower bounds on the I/O cost for full-length RS codes with two and three parities. Furthermore, we build linear repair schemes for the RS codes with improved I/O cost. For full-length RS codes with two parities, our scheme meets the lower bound on the I/O cost.

Purpose: Congenital heart defect (CHD) is the most common birth defect. Thoracic echocardiography (TTE) can provide sufficient cardiac structure information, evaluate hemodynamics and cardiac function, and is an effective method for atrial septal defect (ASD) examination. This paper aims to study a deep learning method based on cardiac ultrasound video to assist in ASD diagnosis. Materials and methods: We select two standard views of the atrial septum (subAS) and low parasternal four-compartment view (LPS4C) as the two views to identify ASD. We enlist data from 300 children patients as part of a double-blind experiment for five-fold cross-validation to verify the performance of our model. In addition, data from 30 children patients (15 positives and 15 negatives) are collected for clinician testing and compared to our model test results (these 30 samples do not participate in model training). We propose an echocardiography video-based atrial septal defect diagnosis system. In our model, we present a block random selection, maximal agreement decision and frame sampling strategy for training and testing respectively, resNet18 and r3D networks are used to extract the frame features and aggregate them to build a rich video-level representation. Results: We validate our model using our private dataset by five-cross validation. For ASD detection, we achieve 89.33 AUC, 84.95 accuracy, 85.70 sensitivity, 81.51 specificity and 81.99 F1 score. Conclusion: The proposed model is multiple instances learning-based deep learning model for video atrial septal defect detection which effectively improves ASD detection accuracy when compared to the performances of previous networks and clinical doctors.

Piggybacking design has been widely applied in distributed storage systems since it can greatly reduce the repair bandwidth with small sub-packetization. Compared with other existing erasure codes, piggybacking is more convenient to operate and the I/O cost is lower. In this paper, we propose a new efficient design which can further reduce the repair bandwidth with the sub-packetization $l\le r$ where $r = n-k$. Generally, we let $l\le 8$. Compared with other analogous designs, our design has lower $l$ and the value of $l$ is more flexible. Moreover, our design can repair all nodes with small repair bandwidth. Therefore our piggybacking design is more feasible., Comment: We have a better idea and this version is not complete

In a modern distributed storage system, storage nodes are organized in racks, and the cross-rack communication dominates the system bandwidth. In We study the rack-aware storage system where all storage nodes are organized in racks and within each rack the nodes can communicate freely without taxing the system bandwidth. Rack-aware regenerating codes (RRCs) were proposed for minimizing the repair bandwidth for single erasures. In the initial setting of RRCs, the repair of a single node requires the participation of all the remaining nodes in the rack containing the failed node as well as a large number of helper racks containing no failures. Consequently, the repair may be infeasible in front of multiple node failures. In this work, a relaxed repair model that can tolerate multiple node failures by simultaneously reducing the intra-rack connections and cross-rack connections is proposed. A tradeoff between the storage and repair bandwidth under the relaxed repair model is derived, and parameters of the two extreme points on the tradeoff curve are characterized for the minimum storage and minimum bandwidth respectively. Moreover, two codes corresponding to the extreme points are explicitly constructed over the fields of size comparable to the code length and with the lowest sub-packetization. Finally, for the convenience of practical use, systematic encoding processes for the two codes are also established., Comment: 13 pages, 2 figures

We consider the rack-aware storage system where $n=\bar{n}u$ nodes are organized in $\bar{n}$ racks each containing $u$ nodes, and any $k=\bar{k}u+u_0~(0\leq u_0n$ which is almost half of the field used in Chen\&Barg's construction. Besides, our code keeps the same access level as Chen\&Barg's low-access construction., Comment: 5 pages, To appear in ITW 2020

In large data centers, storage nodes are organized in racks, and the cross-rack transmission dominates the bandwidth cost. For the repair of single node failures, codes achieving the tradeoff between the storage redundancy and cross-rack repair bandwidth are called rack-aware regenerating codes (RRCs). In this work, we give the first explicit construction of RRCs with the minimum repair bandwidth (i.e., the cross-rack bandwidth equals the storage size per node). Our construction applies to all admissible parameters and has the lowest sub-packetization level. Moreover, the underlying finite fields are of size comparable to the number of storage nodes, which makes our codes more implementable in practice. Finally, for the convenience of practical use, we also establish a transformation to convert our codes into systematic codes., Comment: 7 pages, 2 figure

We consider the rack-aware storage system where \(n\) nodes are organized in \(\bar{n}\) racks each containing \(u\) nodes, and any \(k\) nodes can retrieve the stored file. Moreover, any single node erasure can be recovered by downloading data from \(\bar{d}\) helper racks as well as the remaining \(u\!-\!1\) nodes in the same rack. Previous work mostly focuses on minimizing the cross-rack repair bandwidth under the condition \(\bar{d}\geq \bar{k}\), where \(\bar{k}=\lfloor\frac{k}{u}\rfloor\). However, \(\bar{d}\geq \bar{k}\) is not an intrinsic condition for the rack-aware storage model. In this paper, we establish a tradeoff between the storage overhead and cross-rack repair bandwidth for the particularly interesting case \(\bar{d}\!<\!\bar{k}\). Furthermore, we present explicit constructions of codes with parameters lying on the tradeoff curve respectively at the minimum storage point and minimum bandwidth point. The codes are scalar or have sub-packetization \(\bar{d}\), and operate over finite fields of size comparable to \(n\). Regarding \(\bar{d}\) as the repair degree, these codes combine the advantage of regenerating codes in minimizing the repair bandwidth and that of locally repairable codes in reducing the repair degree. Moreover, they also abandon the restriction of MBR codes having storage overhead no less than \(2\times\) and that of high-rate MSR codes having exponential sub-packetization level., Comment: 5 pages, 1 figures, submitted to ISIT 2021

Suppose a database containing $M$ records is replicated in each of $N$ servers, and a user wants to privately retrieve one record by accessing the servers such that identity of the retrieved record is secret against any up to $T$ servers. A scheme designed for this purpose is called a $T$-private information retrieval ($T$-PIR) scheme. In this paper we focus on the field size of $T$-PIR schemes. We design a generalcapacity-achieving $T$-PIR scheme whose queries are generated by using some {\rm MDS } array codes. It only requires field size $q\geq\sqrt[\ell]{N}$, where $\ell=\min\{t^{M-2},(n-t)^{M-2}\}$, $~t=T/{\rm gcd}(N,T)$,$~n=N/{\rm gcd}(N,T)$ and has the optimal sub-packetization $Nn^{M-2}$. Comparing with existing capacity-achieving $T$-PIR schemes, our scheme has the following advantage, that is, its field size monotonically decreases as the number of records $M$ grows. In particular, the binary field is sufficient for building a capacity-achieving T-PIR scheme as long as $M\geq 2+\lceil\log_\mu\log_2N\rceil$, where $\mu=\min\{t,n-t\}>1$., Comment: 5 pages, Information theory

Dau et al. recently extend Guruswami and Wootters' scheme (STOC'2016) to cooperatively repair two or three erasures in Reed-Solomon (RS) codes. However, their scheme restricts to either the case that the characteristic of $F$ divides the extension degree $[F\!:\!B]$ or some special failure patterns, where $F$ is the base field of the RS code and $B$ is the subfield of the repair symbols. In this paper, we derive an improved cooperative repair scheme that removes all these restrictions. That is, our scheme applies to any characteristic of $F$ and can repair all failure patterns of two or three erasures., Comment: submitted to ISIT2019

An $(n,k,d)$ cooperative regenerating code provides the optimal-bandwidth repair for any $t~(t\!>\!1)$ node failures in a cooperative way. In particular, an MSCR (minimum storage cooperative regenerating) code retains the same storage overhead as an $(n,k)$ MDS code. Suppose each node stores $\alpha$ symbols which indicates the sub-packetization level of the code. A scalar MSCR code attains the minimum sub-packetization, i.e., $\alpha=d-k+t$. By now, all existing constructions of scalar MSCR codes restrict to very special parameters, eg. $d=k$ or $k=2$, etc. In a recent work, Ye and Barg construct MSCR codes for all $n,k,d,t$, however, their construction needs $\alpha\approx{\rm exp}(n^t)$ which is almost infeasible in practice. In this paper, we give an explicit construction of scalar MSCR codes for all $d\geq \max\{2k-1-t,k\}$, which covers all possible parameters except the case of $k\leq d\leq 2k-2-t$ when $k<2k-1-t$. Moreover, as a complementary result, for $k

Suppose a database containing $M$ records is replicated across $N$ servers, and a user wants to privately retrieve one record by accessing the servers such that identity of the retrieved record is secret against any up to $T$ servers. A scheme designed for this purpose is called a $T$-private information retrieval ($T$-PIR) scheme. Three indexes are concerned for PIR schemes: (1)rate, indicating the amount of retrieved information per unit of downloaded data. The highest achievable rate is characterized by the capacity; (2) sub-packetization, reflexing the implementation complexity for linear schemes; (3) field size. We consider linear schemes over a finite field. In this paper, a general $T$-PIR scheme simultaneously attaining the optimality of almost all of the three indexes is presented. Specifically, we design a linear capacity-achieving $T$-PIR scheme with sub-packetization $\!dn^{M-1}\!$ over a finite field $\mathbb{F}_q$, $q\geq N$. The sub-packetization $\!dn^{M-1}\!$, where $\!d\!=\!{\rm gcd}(N,T)\!$ and $\!n\!=\!N/d$, has been proved to be optimal in our previous work. The field size of all existing capacity-achieving $T$-PIR schemes must be larger than $Nt^{M-2}$ where $t=T/d$, while our scheme reduces the field size by an exponential factor., Comment: ISIT 2018