Related papers: Provable Contrastive Continual Learning
Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…
Contrastive self-supervised learning (SSL) learns an embedding space that maps similar data pairs closer and dissimilar data pairs farther apart. Despite its success, one issue has been overlooked: the fairness aspect of representations…
This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…
Training effective text rerankers is crucial for information retrieval. Two strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge from a larger…
Continual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks. In order to alleviate this critical problem…
Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality…
Most fine-grained fashion image retrieval (FIR) methods assume a static setting, requiring full retraining when new attributes appear, which is costly and impractical for dynamic scenarios. Although pretrained models support zero-shot…
Recent work using pretrained transformers has shown impressive performance when fine-tuned with data from the downstream problem of interest. However, they struggle to retain that performance when the data characteristics changes. In this…
Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), models often struggle to balance learning new tasks (plasticity)…
The recent breakthrough achieved by contrastive learning accelerates the pace for deploying unsupervised training on real-world data applications. However, unlabeled data in reality is commonly imbalanced and shows a long-tail distribution,…
Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption…
One of the successful approaches in semi-supervised learning is based on the consistency regularization. Typically, a student model is trained to be consistent with teacher prediction for the inputs under different perturbations. To be…
The continual learning problem has been widely studied in image classification, while rare work has been explored in object detection. Some recent works apply knowledge distillation to constrain the model to retain old knowledge, but this…
Contrastive Learning first extracts features from unlabeled data, followed by linear probing with labeled data. Adversarial Contrastive Learning (ACL) integrates Adversarial Training into the first phase to enhance feature robustness…
Contrastive learning (CL) has recently emerged as an effective approach to learning representation in a range of downstream tasks. Central to this approach is the selection of positive (similar) and negative (dissimilar) sets to provide the…
Replay-based continual learning (CL) methods assume that models trained on a small subset can also effectively minimize the empirical risk of the complete dataset. These methods maintain a memory buffer that stores a sampled subset of data…
Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evaluation protocol for CIL algorithms is to measure the average…
In recent times, contrastive learning based loss functions have become increasingly popular for visual self-supervised representation learning owing to their state-of-the-art (SOTA) performance. Most of the modern contrastive learning…
The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained…
Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…