Related papers: ELM: Embedding and Logit Margins for Long-Tail Lea…
The multi-label classification problem has generated significant interest in recent years. However, existing approaches do not adequately address two key challenges: (a) the ability to tackle problems with a large number (say millions) of…
Real-world data often exhibits a long-tailed distribution, in which head classes occupy most of the data, while tail classes only have very few samples. Models trained on long-tailed datasets have poor adaptability to tail classes and the…
Deep neural network models degrade significantly in the long-tailed data distribution, with the overall training data dominated by a small set of classes in the head, and the tail classes obtaining less training examples. Addressing the…
Learning generalizable representation and classifier for class-imbalanced data is challenging for data-driven deep models. Most studies attempt to re-balance the data distribution, which is prone to overfitting on tail classes and…
The distribution of data in the world (eg, internet, etc.) significantly differs from the well-curated datasets and is often over-populated with samples from common categories. The algorithms designed for well-curated datasets perform…
Deep learning-based models encounter challenges when processing long-tailed data in the real world. Existing solutions usually employ some balancing strategies or transfer learning to deal with the class imbalance problem, based on the…
The Extreme Learning Machine (ELM) is a single-hidden layer feedforward neural network (SLFN) learning algorithm that can learn effectively and quickly. The ELM training phase assigns the input weights and bias randomly and does not change…
Real-world data are long-tailed, the lack of tail samples leads to a significant limitation in the generalization ability of the model. Although numerous approaches of class re-balancing perform well for moderate class imbalance problems,…
To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model…
Unlike the case when using a balanced training dataset, the per-class recall (i.e., accuracy) of neural networks trained with an imbalanced dataset are known to vary a lot from category to category. The convention in long-tailed recognition…
Sequential Recommendation (SR) learns user preferences from their historical interaction sequences and provides personalized suggestions. In real-world scenarios, most items exhibit sparse interactions, known as the tail-item problem. This…
In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated remarkable capabilities among various methods. This paradigm decouples the training process into separate representation learning and classifier…
Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding space. We relate DML to feasibility problem of finite chance constraints. We show that minimizer…
With the emergence of deep learning, metric learning has gained significant popularity in numerous machine learning tasks dealing with complex and large-scale datasets, such as information retrieval, object recognition and recommendation…
Multi-label classification (MLC) refers to the problem of tagging a given instance with a set of relevant labels. Most existing MLC methods are based on the assumption that the correlation of two labels in each label pair is symmetric,…
This paper presents an investigation into long-tail video recognition. We demonstrate that, unlike naturally-collected video datasets and existing long-tail image benchmarks, current video benchmarks fall short on multiple long-tailed…
Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges that demand abundant annotations. However, in fields that rely on professional knowledge, such as medicine and…
Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample. However, annotating label distribution (LD) for training samples is extremely costly. So recent…
We analyze neural scaling laws in a solvable model of last-layer fine-tuning where targets have intrinsic, instance-heterogeneous difficulty. In our Latent Instance Difficulty (LID) model, each input's target variance is governed by a…
Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories. In this paper, we propose a novel generative and fine-tuning framework,…