In the incremental detection task, unlike the incremental classification
task, data ambiguity exists due to the possibility of an image having different
labeled bounding boxes in multiple continuous learning stages. This phenomenon
often impairs the model's ability to learn new classes. However, the forward
compatibility of the model is less considered in existing work, which hinders
the model's suitability for incremental learning. To overcome this obstacle, we
propose to use a language-visual model such as CLIP to generate text feature
embeddings for different class sets, which enhances the feature space globally.
We then employ the broad classes to replace the unavailable novel classes in
the early learning stage to simulate the actual incremental scenario. Finally,
we use the CLIP image encoder to identify potential objects in the proposals,
which are classified into the background by the model. We modify the background
labels of those proposals to known classes and add the boxes to the training
set to alleviate the problem of data ambiguity. We evaluate our approach on
various incremental learning settings on the PASCAL VOC 2007 dataset, and our
approach outperforms state-of-the-art methods, particularly for the new
classes.

通过使用 CLIP 等语言 - 视觉模型生成不同类别集合的文本特征嵌入来改善特征空间，用广义类别替换早期学习阶段中的不可用新类别，从而模拟实际增量情景，并使用 CLIP 图像编码器识别提议中的潜在对象并对其进行分类，通过修改提议的背景标签为已知类别并将框添加到训练集来缓解数据模糊性问题，我们在 PASCAL VOC 2007 数据集上评估了我们的方法，在各种增量学习设置中，我们的方法优于最先进的方法，特别是对于新的类别。

使用 CLIP 的增量目标检测

Incremental Object Detection with CLIP

Spontaneous spoken dialogue is often disfluent, containing pauses,
hesitations, self-corrections and false starts. Processing such phenomena is
essential in understanding a speaker's intended meaning and controlling the
flow of the conversation. Furthermore, this processing needs to be word-by-word
incremental to allow further downstream processing to begin as early as
possible in order to handle real spontaneous human conversational behaviour.
In addition, from a developer's point of view, it is highly desirable to be
able to develop systems which can be trained from `clean' examples while also
able to generalise to the very diverse disfluent variations on the same data --
thereby enhancing both data-efficiency and robustness. In this paper, we
present a multi-task LSTM-based model for incremental detection of disfluency
structure, which can be hooked up to any component for incremental
interpretation (e.g. an incremental semantic parser), or else simply used to
`clean up' the current utterance as it is being produced.
We train the system on the Switchboard Dialogue Acts (SWDA) corpus and
present its accuracy on this dataset. Our model outperforms prior neural
network-based incremental approaches by about 10 percentage points on SWDA
while employing a simpler architecture. To test the model's generalisation
potential, we evaluate the same model on the bAbI+ dataset, without any
additional training. bAbI+ is a dataset of synthesised goal-oriented dialogues
where we control the distribution of disfluencies and their types. This shows
that our approach has good generalisation potential, and sheds more light on
which types of disfluency might be amenable to domain-general processing.

本文提出一种多任务基于 LSTM 的模型，用于增量检测口吃结构，可以连接到任何组件以进行增量解释，或者在产生当前话语时用于 “清理” 当前话语。我们在 Switchboard 对话行为语料库上训练了该系统，并展示了其在该数据集上的准确性。我们的模型在 SWDA 上比以前的神经网络基于增量的方法表现优异，同时采用较简单的架构。为了测试模型的泛化潜力，我们在没有任何附加训练的情况下，在 bAbI + 数据集上评估了相同的模型。这表明我们的方法具有很好的泛化潜力，并更加详细地阐明了哪些类型的口吃可能适合于领域通用处理。