Related papers: Alleviating Representational Shift for Continual F…

Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities.…

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised…

Distribution shift (e.g., task or domain shift) in continual learning (CL) usually results in catastrophic forgetting of neural networks. Although it can be alleviated by repeatedly replaying buffered data, the every-step replay is…

Batch Normalization (BN) has become a core design block of modern Convolutional Neural Networks (CNNs). A typical modern CNN has a large number of BN layers in its lean and deep architecture. BN requires mean and variance calculations over…

Parameter Efficient Fine-Tuning (PEFT) techniques have drawn significant attention due to their ability to yield competitive results while updating only a small portion of the adjustable parameters. However, existing PEFT methods pose…

A deep convolutional neural network (CNN) has been widely used in image classification and gives better classification accuracy than the other techniques. The softmax cross-entropy loss function is often used for classification tasks. There…

Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…

Neural Implicit Representation (NIR) has recently gained significant attention due to its remarkable ability to encode complex and high-dimensional data into representation space and easily reconstruct it through a trainable mapping…

Deep Neural Network (DNN) has achieved great success on datasets of closed class set. However, new classes, like new categories of social media topics, are continuously added to the real world, making it necessary to incrementally learn.…

This paper tackles the problem of learning a finer representation than the one provided by training labels. This enables fine-grained category retrieval of images in a collection annotated with coarse labels only. Our network is learned…

Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the…

Parameter-efficient fine-tuning (PEFT) has become a common method for fine-tuning large language models, where a base model can serve multiple users through PEFT module switching. To enhance user experience, base models require periodic…

Learning discriminative deep feature embeddings by using million-scale in-the-wild datasets and margin-based softmax loss is the current state-of-the-art approach for face recognition. However, the memory and computing cost of the Fully…

Conventional model upgrades for visual search systems require offline refresh of gallery features by feeding gallery images into new models (dubbed as "backfill"), which is time-consuming and expensive, especially in large-scale…

Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples. Specifically,…

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism's complexity scales quadratically with sequence length.…

Representing surfaces as zero level sets of neural networks recently emerged as a powerful modeling paradigm, named Implicit Neural Representations (INRs), serving numerous downstream applications in geometric deep learning and 3D vision.…

Transformer-based language models create hidden representations of their inputs at every layer, but only use final-layer representations for prediction. This obscures the internal decision-making process of the model and the utility of its…

Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer…