Related papers: Transfer Hashing with Privileged Information

In large scale systems, approximate nearest neighbour search is a crucial algorithm to enable efficient data retrievals. Recently, deep learning-based hashing algorithms have been proposed as a promising paradigm to enable data dependent…

Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste bits on layers that are less relevant to the task signal…

The availability of abundant labeled data in recent years led the researchers to introduce a methodology called transfer learning, which utilizes existing data in situations where there are difficulties in collecting new annotated data.…

Supervised learning datasets often have privileged information, in the form of features which are available at training time but are not available at test time e.g. the ID of the annotator that provided the label. We argue that privileged…

Large language models with billions of parameters are often over-provisioned: many layers contribute little unique information yet dominate the memory and energy footprint during inference. We present LieQ Layer-wise information…

This paper describes a new approach, called Terminological Bucket Indexing (TBI), for efficient indexing and retrieval of both nested and super terms using a single method. We propose a hybrid data structure for facilitating faster indexing…

Mixed-precision quantization (MPQ) is crucial for deploying deep neural networks on resource-constrained devices, but finding the optimal bit-width for each layer represents a complex combinatorial optimization problem. Current…

To tackle the huge computational demand of large foundation models, activation-aware compression techniques without retraining have been introduced. However, since these methods highly rely on calibration data, domain shift issues may arise…

Decentralized collaborative learning under data heterogeneity and privacy constraints has rapidly advanced. However, existing solutions like federated learning, ensembles, and transfer learning, often fail to adequately serve the unique…

Several deep supervised hashing techniques have been proposed to allow for efficiently querying large image databases. However, deep supervised image hashing techniques are developed, to a great extent, heuristically often leading to…

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by…

We introduce a new unsupervised anomaly detection ensemble called SPI which can harness privileged information - data available only for training examples but not for (future) test examples. Our ideas build on the Learning Using Privileged…

Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement…

Hyperspectral image (HSI) classification is one of the most active research topics and has achieved promising results boosted by the recent development of deep learning. However, most state-of-the-art approaches tend to perform poorly when…

Unsupervised hashing can desirably support scalable content-based image retrieval (SCBIR) for its appealing advantages of semantic label independence, memory and search efficiency. However, the learned hash codes are embedded with limited…

We present three related ways of using Transfer Learning to improve feature selection. The three methods address different problems, and hence share different kinds of information between tasks or feature classes, but all three are based on…

Classification models may often suffer from "structure imbalance" between training and testing data that may occur due to the deficient data collection process. This imbalance can be represented by the learning using privileged information…

As the size $n$ of datasets become massive, many commonly-used clustering algorithms (for example, $k$-means or hierarchical agglomerative clustering (HAC) require prohibitive computational cost and memory. In this paper, we propose a…

Table question answering (TQA) focuses on answering questions based on tabular data. Developing TQA systems targets effective interaction with tabular data for tasks such as cell retrieval and data analysis. While recent work has leveraged…

Expanding existing learning systems to provide high-quality customized models for more domains, such as new users, is challenged by the limited labeled data and the data and device heterogeneities. While knowledge distillation methods could…