Related papers: AutoLoss-Zero: Searching Loss Functions from Scrat…

Classical lens design minimizes optical aberrations to produce sharp images, but is typically decoupled from downstream computer vision tasks. Existing end-to-end optical design learns optical encoding through joint optimization, but often…

The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly.…

Finding deletion-correcting codes of maximum size has been an open problem for over 70 years, even for a single deletion. In this paper, we propose a novel approach for constructing deletion-correcting codes. A code is a set of sequences…

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes.…

Traditional task-oriented dialog (ToD) systems rely heavily on labor-intensive turn-level annotations, such as dialogue states and policy labels, for training. This work explores whether large language models (LLMs) can be fine-tuned solely…

In the field of visual scene understanding, deep neural networks have made impressive advancements in various core tasks like segmentation, tracking, and detection. However, most approaches operate on the close-set assumption, meaning that…

Automatic segmentation methods are an important advancement in medical image analysis. Machine learning techniques, and deep neural networks in particular, are the state-of-the-art for most medical image segmentation tasks. Issues with…

A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this paper, we provide a general weighting framework for understanding recent…

Foundation Models (FMs) have demonstrated unprecedented capabilities including zero-shot learning, high fidelity data synthesis, and out of domain generalization. However, as we show in this paper, FMs still have poor out-of-the-box…

Cross-entropy loss is the standard metric used to train classification models in deep learning and gradient boosting. It is well-known that this loss function fails to account for similarities between the different values of the target. We…

Home-assistant robots have been a long-standing research topic, and one of the biggest challenges is searching for required objects in housing environments. Previous object-goal navigation requires the robot to search for a target object…

Neural networks are increasingly used in environmental science applications. Furthermore, neural network models are trained by minimizing a loss function, and it is crucial to choose the loss function very carefully for environmental…

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes.…

A model's capacity to generalize its knowledge to interpret unseen inputs with different characteristics is crucial to build robust and reliable machine learning systems. Language model evaluation tasks lack information metrics about model…

Supervised fine-tuning (SFT) of large language models (LLMs) for specialized tasks requires high-quality datasets, but manual curation is prohibitively expensive. Synthetic data generation offers scalability, but its effectiveness relies on…

Almost all neural architecture search methods are evaluated in terms of performance (i.e. test accuracy) of the model structures that it finds. Should it be the only metric for a good autoML approach? To examine aspects beyond performance,…

Causal machine-learning is about predicting the net-effect (true-lift) of treatments. Given the data of a treatment group and a control group, it is similar to a standard supervised-learning problem. Unfortunately, there is no similarly…

Task incremental learning aims to enable a system to maintain its performance on previously learned tasks while learning new tasks, solving the problem of catastrophic forgetting. One promising approach is to build an individual network or…

An important goal of AutoML is to automate-away the design of neural networks on new tasks in under-explored domains. Motivated by this goal, we study the problem of enabling users to discover the right neural operations given data from…

Ranking is a key aspect of many applications, such as information retrieval, question answering, ad placement and recommender systems. Learning to rank has the goal of estimating a ranking model automatically from training data. In…