Related papers: Early Preparation Pays Off: New Classifier Pre-tun…
Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…
Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…
Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance…
Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles…
Continual learning (CL) aims to equip models with the ability to learn from a stream of tasks without forgetting previous knowledge. With the progress of vision-language models like Contrastive Language-Image Pre-training (CLIP), their…
We address the problem of incremental sequence classification, where predictions are updated as new elements in the sequence are revealed. Drawing on temporal-difference learning from reinforcement learning, we identify a…
Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in…
We present a neural semi-supervised learning model termed Self-Pretraining. Our model is inspired by the classic self-training algorithm. However, as opposed to self-training, Self-Pretraining is threshold-free, it can potentially update…
Recently, CLIP-based approaches have exhibited remarkable performance on generalization and few-shot learning tasks, fueled by the power of contrastive language-vision pre-training. In particular, prompt tuning has emerged as an effective…
We propose a novel class incremental learning approach by incorporating a feature augmentation technique motivated by adversarial attacks. We employ a classifier learned in the past to complement training examples rather than simply play a…
The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability in their training…
In this paper, we propose a method to improve prediction accuracy of semantic segmentation methods as follows: (1) construct a neural network that has pre-processing layers based on a convolutional autoencoder ahead of a semantic…
Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The…
With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost…
Parameter-Efficient Fine-Tuning (PEFT) methods have gained significant popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks, primarily due to their potential to significantly reduce memory and computational…
Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…
Medical image segmentation is a vital healthcare endeavor requiring precise and efficient models for appropriate diagnosis and treatment. Vision transformer (ViT)-based segmentation models have shown great performance in accomplishing this…
Early action prediction seeks to anticipate an action before it fully unfolds, but limited visual evidence makes this task especially challenging. We introduce EAST, a simple and efficient framework that enables a model to reason about…
Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves…
With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting…