Introducing language guidance in prompt-based continual learning
Continual Learning aims to learn a single model on a sequence of tasks without having
access to data from previous tasks. The biggest challenge in the domain still remains …
access to data from previous tasks. The biggest challenge in the domain still remains …
I2mvformer: Large language model generated multi-view document supervision for zero-shot image classification
Recent works have shown that unstructured text (documents) from online sources can serve
as useful auxiliary information for zero-shot image classification. However, these methods …
as useful auxiliary information for zero-shot image classification. However, these methods …
Graph knows unknowns: Reformulate zero-shot learning as sample-level graph recognition
Zero-shot learning (ZSL) is an extreme case of transfer learning that aims to recognize
samples (eg, images) of unseen classes relying on a train-set covering only seen classes …
samples (eg, images) of unseen classes relying on a train-set covering only seen classes …
Hierarchical visual primitive experts for compositional zero-shot learning
Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior
knowledge of known primitives (attribute and object). Previous works for CZSL often suffer …
knowledge of known primitives (attribute and object). Previous works for CZSL often suffer …
AAPL: Adding Attributes to Prompt Learning for Vision-Language Models
G Kim, S Kim, S Lee - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Recent advances in large pre-trained vision-language models have demonstrated
remarkable performance on zero-shot downstream tasks. Building upon this recent studies …
remarkable performance on zero-shot downstream tasks. Building upon this recent studies …
Troika: Multi-path cross-modal traction for compositional zero-shot learning
Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language
models (VLMs) by constructing trainable prompts only for composed state-object pairs …
models (VLMs) by constructing trainable prompts only for composed state-object pairs …
Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning
Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object
compositions by learning from seen compositions. Composing the learned knowledge of …
compositions by learning from seen compositions. Composing the learned knowledge of …
Parsnets: A parsimonious orthogonal and low-rank linear networks for zero-shot learning
This paper provides a novel parsimonious yet efficient design for zero-shot learning (ZSL),
dubbed ParsNets, where we are interested in learning a composition of on-device friendly …
dubbed ParsNets, where we are interested in learning a composition of on-device friendly …
Does continual learning meet compositionality? new benchmarks and an evaluation framework
Compositionality facilitates the comprehension of novel objects using acquired concepts
and the maintenance of a knowledge pool. This is particularly crucial for continual learners …
and the maintenance of a knowledge pool. This is particularly crucial for continual learners …
Simple primitives with feasibility-and contextuality-dependence for open-world compositional zero-shot learning
The task of Open-World Compositional Zero-Shot Learning (OW-CZSL) is to recognize novel
state-object compositions in images from all possible compositions, where the novel …
state-object compositions in images from all possible compositions, where the novel …